Understanding how humans leverage semantic knowledge to navigate unfamiliar
environments and decide where to explore next is pivotal for developing robots capable of …

Open-vocabulary 3D instance segmentation is cutting-edge for its ability to segment 3D
instances without predefined categories. However progress in 3D lags behind its 2D …

In this paper we propose a new framework for online 3D scene perception. Conventional 3D
scene perception methods are offline ie take an already reconstructed 3D scene geometry …

Object Goal Navigation (ObjectNav) aims at directing an agent to a specified target object
within an unseen scene. This task integrates advanced techniques, including visual …

As a new embodied vision task Instance ImageGoal Navigation (IIN) aims to navigate to a
specified object depicted by a goal image in an unexplored environment. The main …

Semantic 3D mapping, the process of fusing depth and image segmentation information
between multiple views to build 3D maps annotated with object classes in real-time, is a …

Mobile manipulation constitutes a fundamental task for robotic assistants and garners
significant attention within the robotics community. A critical challenge inherent in mobile …

Abstract The Object Goal navigation (ObjectNav) task requires the agent to navigate to a
specified target in an unseen environment. Since the environment layout is unknown the …

Local feature matching enjoys wide-ranging applications in the realm of computer vision,
encompassing domains such as image retrieval, 3D reconstruction, and object recognition …

Abstract Target-Driven Semantic Navigation (TDSN) shows great potential to be applied in
intelligent domestic assistants supporting humans with daily activities. Although numerous …